# Weather Classification on MWI 20k (10% train)

Source: [Weather Classification on MWI 20k (10% train)](<https://www.sota2.com/research/sota/weather-classification-on-mwi-20k-10-percent-train>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-20T08:26:25.305Z

Evaluation of Weather Classification performance using the 10% training subset of the MWI 20k dataset, measured by Accuracy.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Weather Classification |
| Dataset (including any stated split) | MWI 20k (10% train) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Accuracy](<https://www.sota2.com/research/sota/weather-classification-on-mwi-20k-10-percent-train.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| SLM3 | 90.01 | Not recorded | 69e5b3237d0172140ec7e0bd |
| ST-STORM | 84.92 | Not recorded | 69e5b3237d0172140ec7e0bd |
| MoCo-v3 | 70 | Not recorded | 69e5b3237d0172140ec7e0bd |
| I-JEPA | 64.66 | Not recorded | 69e5b3237d0172140ec7e0bd |

### SLM3

Accuracy: 90.01. Result ID: 69e5e32d47f34ce924cc07bd.

[Reporting paper](<https://www.sota2.com/research/paper/69e5b3237d0172140ec7e0bd.md>)

Recorded evaluation configuration: {"Regime":"Supervised","State of the art":"true"}. This record does not assert independent reproduction.

### ST-STORM

Accuracy: 84.92. Result ID: 69e5e32d47f34ce924cc07bc.

[Reporting paper](<https://www.sota2.com/research/paper/69e5b3237d0172140ec7e0bd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e5b3237d0172140ec7e0bd.md>)

Recorded evaluation configuration: {"Encoder":"Frozen","Protocol":"Fine-tuning on 10% of training data","Branch":"Style"}. This record does not assert independent reproduction.

### MoCo-v3

Accuracy: 70. Result ID: 69e5e32d47f34ce924cc07bb.

[Reporting paper](<https://www.sota2.com/research/paper/69e5b3237d0172140ec7e0bd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a931e209131cea2903d.md>)

[Implementation](<https://github.com/facebookresearch/moco-v3>)

Recorded evaluation configuration: {"Encoder":"Frozen","Protocol":"Fine-tuning on 10% of training data"}. This record does not assert independent reproduction.

### I-JEPA

Accuracy: 64.66. Result ID: 69e5e32d47f34ce924cc07ba.

[Reporting paper](<https://www.sota2.com/research/paper/69e5b3237d0172140ec7e0bd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f061e209131cea43581.md>)

Recorded evaluation configuration: {"Encoder":"Frozen","Protocol":"Fine-tuning on 10% of training data"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
